{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PEZTGLNYARRJY6R7Z3RH6FBRT7","short_pith_number":"pith:PEZTGLNY","schema_version":"1.0","canonical_sha256":"7933332db804629c7a3fcee27f14319fe4e509b0c73434f7fc98a212dcfc353f","source":{"kind":"arxiv","id":"2606.29898","version":1},"attestation_state":"computed","paper":{"title":"Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haoxu Huang, Jiacheng You, Tongsam Zheng, Yang Gao, Yifan Chen","submitted_at":"2026-06-29T07:34:39Z","abstract_excerpt":"Real-world evaluation is the gold standard for robot policies because it tests them against the physical conditions and deployment challenges they are ultimately designed to handle. However, real-world evaluation is also the bottleneck for iterating on robot policies: it is costly, difficult to reproduce, and often too sparse to reliably compare nearby model variants. A straightforward proxy for performance is validation loss on expert demonstrations, but this proxy is often poorly correlated with real-world performance. In this paper, we introduce Critical Interval MSE (CI-MSE), an intuitivel"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.29898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:34:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93fa1061b7bfa78a496357211e33fbeee46c06a86c3a56175acaac7c99bcb6a0","abstract_canon_sha256":"bb21a3a9b39ef86ebafaa8c9a863585e5e5d465caeb28b701a1450e374116494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:39.996590Z","signature_b64":"lmavswGv4bluALIEcdBlUYF+8mF/aazh7E3evU1hoAOTdiY7TVACStikaolbvZyHQCWixrjl0f/gJ9MK4bT5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7933332db804629c7a3fcee27f14319fe4e509b0c73434f7fc98a212dcfc353f","last_reissued_at":"2026-06-30T02:17:39.996063Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:39.996063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haoxu Huang, Jiacheng You, Tongsam Zheng, Yang Gao, Yifan Chen","submitted_at":"2026-06-29T07:34:39Z","abstract_excerpt":"Real-world evaluation is the gold standard for robot policies because it tests them against the physical conditions and deployment challenges they are ultimately designed to handle. However, real-world evaluation is also the bottleneck for iterating on robot policies: it is costly, difficult to reproduce, and often too sparse to reliably compare nearby model variants. A straightforward proxy for performance is validation loss on expert demonstrations, but this proxy is often poorly correlated with real-world performance. In this paper, we introduce Critical Interval MSE (CI-MSE), an intuitivel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29898","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.29898/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.29898","created_at":"2026-06-30T02:17:39.996141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29898v1","created_at":"2026-06-30T02:17:39.996141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29898","created_at":"2026-06-30T02:17:39.996141+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEZTGLNYARRJ","created_at":"2026-06-30T02:17:39.996141+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEZTGLNYARRJY6R7","created_at":"2026-06-30T02:17:39.996141+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEZTGLNY","created_at":"2026-06-30T02:17:39.996141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7","json":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7.json","graph_json":"https://pith.science/api/pith-number/PEZTGLNYARRJY6R7Z3RH6FBRT7/graph.json","events_json":"https://pith.science/api/pith-number/PEZTGLNYARRJY6R7Z3RH6FBRT7/events.json","paper":"https://pith.science/paper/PEZTGLNY"},"agent_actions":{"view_html":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7","download_json":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7.json","view_paper":"https://pith.science/paper/PEZTGLNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29898&json=true","fetch_graph":"https://pith.science/api/pith-number/PEZTGLNYARRJY6R7Z3RH6FBRT7/graph.json","fetch_events":"https://pith.science/api/pith-number/PEZTGLNYARRJY6R7Z3RH6FBRT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7/action/storage_attestation","attest_author":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7/action/author_attestation","sign_citation":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7/action/citation_signature","submit_replication":"https://pith.science/pith/PEZTGLNYARRJY6R7Z3RH6FBRT7/action/replication_record"}},"created_at":"2026-06-30T02:17:39.996141+00:00","updated_at":"2026-06-30T02:17:39.996141+00:00"}